INDEX

Explanations

references to the letter 'T' in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ask

-0.17

ipo

-0.16

asks

-0.16

parcel

-0.15

ASK

-0.15

ouver

-0.15

acen

-0.14

ouses

-0.14

tÄĽ

-0.14

 Sund

-0.14

POSITIVE LOGITS

bones

0.20

Rex

0.20

rex

0.19

werk

0.19

 Bone

0.19

rolls

0.19

elly

0.18

 Pain

0.18

rolled

0.18

rolling

0.17

Activations Density 0.032%

references to the letter 'T' in various contexts

No Comments

No Known Activations